© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48611
    Prev
    Next
    INDEX
    Explanations

    citations and references `[[` followed by `[`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.10
    en
    -0.09
    èĩªå·±
    -0.09
    ت
    -0.08
    ird
    -0.07
    ständige
    -0.07
    ity
    -0.07
    	č↵č↵
    -0.07
    िव
    -0.06
    enzen
    -0.06
    POSITIVE LOGITS
    paring
    0.10
    plorer
    0.09
    poons
    0.08
    лав
    0.08
    åĸĥ
    0.08
    duino
    0.08
    utip
    0.08
    lotte
    0.07
    ạo
    0.07
    kev
    0.07
    Activations Density 0.003%

    No Known Activations